import time import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import MiniBatchKMeans, KMeans from sklearn.metrics.pairwise import pairwise_distances_argmin from sklearn.datasets import make_blobs # Generate sample data np.random.seed(0) batch_size = 45 centers = [[1, 1], [-1, -1], [1, -1]] n_clusters = len(centers) X, labels_true = make_blobs(n_samples=3000, centers=centers, cluster_std=0.7) # Compute clustering with Means k_means = KMeans(init='k-means++', n_clusters=3, n_init=10) t0 = time.time() k_means.fit(X) t_batch = time.time() - t0 # Compute clustering with MiniBatchKMeans mbk = MiniBatchKMeans(init='k-means++', n_clusters=3, batch_size=batch_size, n_init=10, max_no_improvement=10, verbose=0) t0 = time.time() mbk.fit(X) t_mini_batch = time.time() - t0 # Plot result fig = plt.figure(figsize=(8, 3)) fig.subplots_adjust(left=0.02, right=0.98, bottom=0.05, top=0.9) colors = ['#4EACC5', '#FF9C34', '#4E9A06'] # We want to have the same colors for the same cluster from the # MiniBatchKMeans and the KMeans algorithm. Let's pair the cluster centers per # closest one. k_means_cluster_centers = k_means.cluster_centers_ order = pairwise_distances_argmin(k_means.cluster_centers_, mbk.cluster_centers_) mbk_means_cluster_centers = mbk.cluster_centers_[order] k_means_labels = pairwise_distances_argmin(X, k_means_cluster_centers) mbk_means_labels = pairwise_distances_argmin(X, mbk_means_cluster_centers) # KMeans for k, col in zip(range(n_clusters), colors): my_members = k_means_labels == k cluster_center = k_means_cluster_centers[k] plt.plot(X[my_members, 0], X[my_members, 1], 'w', markerfacecolor=col, marker='.') plt.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col, markeredgecolor='k', markersize=6) plt.title('KMeans') plt.xticks(()) plt.yticks(()) plt.show() 这段代码每一句在干什么
时间: 2024-02-24 15:00:01 浏览: 201
这段代码主要是使用Scikit-learn库中的KMeans和MiniBatchKMeans算法对生成的样本数据进行聚类,并通过可视化方式展示聚类结果。
具体每一句代码的作用如下:
1. 导入所需的库和模块
```
import time
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import MiniBatchKMeans, KMeans
from sklearn.metrics.pairwise import pairwise_distances_argmin
from sklearn.datasets import make_blobs
```
2. 生成样本数据
```
batch_size = 45
centers = [[1, 1], [-1, -1], [1, -1]]
n_clusters = len(centers)
# 生成样本数据
X, labels_true = make_blobs(n_samples=3000, centers=centers, cluster_std=0.7)
```
3. 使用KMeans算法进行聚类
```
# 初始化KMeans模型
k_means = KMeans(init='k-means++', n_clusters=3, n_init=10)
# 训练KMeans模型
t0 = time.time()
k_means.fit(X)
t_batch = time.time() - t0
```
4. 使用MiniBatchKMeans算法进行聚类
```
# 初始化MiniBatchKMeans模型
mbk = MiniBatchKMeans(init='k-means++', n_clusters=3, batch_size=batch_size,
n_init=10, max_no_improvement=10, verbose=0)
# 训练MiniBatchKMeans模型
t0 = time.time()
mbk.fit(X)
t_mini_batch = time.time() - t0
```
5. 可视化聚类结果
```
# 可视化KMeans聚类结果
fig = plt.figure(figsize=(8, 3))
fig.subplots_adjust(left=0.02, right=0.98, bottom=0.05, top=0.9)
colors = ['#4EACC5', '#FF9C34', '#4E9A06']
k_means_cluster_centers = k_means.cluster_centers_
order = pairwise_distances_argmin(k_means.cluster_centers_, mbk.cluster_centers_)
mbk_means_cluster_centers = mbk.cluster_centers_[order]
k_means_labels = pairwise_distances_argmin(X, k_means_cluster_centers)
mbk_means_labels = pairwise_distances_argmin(X, mbk_means_cluster_centers)
for k, col in zip(range(n_clusters), colors):
my_members = k_means_labels == k
cluster_center = k_means_cluster_centers[k]
plt.plot(X[my_members, 0], X[my_members, 1], 'w',
markerfacecolor=col, marker='.')
plt.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col,
markeredgecolor='k', markersize=6)
plt.title('KMeans')
plt.xticks(())
plt.yticks(())
plt.show()
```
以上就是这段代码的每一句话的作用。
阅读全文